The Deletable Bloom filter: A new member of the Bloom family

TL;DR

The paper presents the Deletable Bloom filter, a novel data structure that allows false-negative-free deletions with reduced memory usage, enhancing probabilistic filter applications.

Contribution

It introduces the Deletable Bloom filter, a new variant that efficiently supports deletions without false negatives, improving upon existing Bloom filter designs.

Findings

Enables false-negative-free deletions

Reduces memory consumption compared to traditional Bloom filters

Suitable for probabilistic filter applications

Abstract

We introduce the Deletable Bloom filter (DlBF) as a new spin on the popular data structure based on compactly encoding the information of where collisions happen when inserting elements. The DlBF design enables false-negative-free deletions at a fraction of the cost in memory consumption, which turns to be appealing for certain probabilistic filter applications.